paper-with-me

홈 › Papers

NeuroADDA: Active Discriminative Domain Adaptation in Connectomic

2025-03-08 · Shashata Sawmya, Thomas L. Athey, Gwyneth Liu, Nir Shavit

Training segmentation models from scratch has been the standard approach for new electron microscopy connectomics datasets. However, leveraging pretrained models from existing datasets could improve efficiency and performance in constrained annotation budget. In this study, we investigate domain adaptation in connectomics by analyzing six major datasets spanning different organisms. We show that, Maximum Mean Discrepancy (MMD) between neuron image distributions serves as a reliable indicator of transferability, and identifies the optimal source domain for transfer learning. Building on this, we introduce NeuroADDA, a method that combines optimal domain selection with source-free active learning to effectively adapt pretrained backbones to a new dataset. NeuroADDA consistently outperforms training from scratch across diverse datasets and fine-tuning sample sizes, with the largest gain observed at $n=4$ samples with a 25-67\% reduction in Variation of Information. Finally, we show that our analysis of distributional differences among neuron images from multiple species in a learned feature space reveals that these domain "distances" correlate with phylogenetic distance among those species.

📄 PDF Abstract BibTeX arXiv:2503.06196

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningDomain AdaptationTransfer Learning

Similar Papers 제목 키워드 기반

An Out-of-Domain Synapse Detection Challenge for Microwasp Brain Connectomes

2023-02-01 · Jingpeng Wu, Yicong Li, Nishika Gupta, Kazunori Shinomiya 외

The size of image stacks in connectomics studies now reaches the terabyte and often petabyte scales with a great diversity of appearance across brain regions and samples. However, manual annotation of neural structures, …

DiversityDomain Adaptation

Discriminative Active Learning for Domain Adaptation

2020-05-24 · Fan Zhou, Changjian Shui, Bincheng Huang, Boyu Wang 외

Domain Adaptation aiming to learn a transferable feature between different but related domains has been well investigated and has shown excellent empirical performances. Previous works mainly focused on matching the marg…

Active LearningDiversityDomain Adaptation

Active Adversarial Domain Adaptation

2019-04-16 · Jong-Chyi Su, Yi-Hsuan Tsai, Kihyuk Sohn, Buyu Liu 외

We propose an active learning approach for transferring representations across domains. Our approach, active adversarial domain adaptation (AADA), explores a duality between two related problems: adversarial domain align…

Active LearningDiversityDomain Adaptationobject-detection+2

An In-Depth Analysis of Adversarial Discriminative Domain Adaptation for Digit Classification

2024-12-27 · Eugene Choi, Julian Rodriguez, Edmund Young

Domain adaptation is an active area of research driven by the growing demand for robust machine learning models that perform well on real-world data. Adversarial learning for deep neural networks (DNNs) has emerged as a …

ClassificationDomain Adaptationdomain classificationimage-classification+1

Active Multi-Kernel Domain Adaptation for Hyperspectral Image Classification

2019-04-10 · Cheng Deng, Xianglong Liu, Chao Li, DaCheng Tao

Recent years have witnessed the quick progress of the hyperspectral images (HSI) classification. Most of existing studies either heavily rely on the expensive label information using the supervised learning or can hardly…

Active LearningClassificationDomain AdaptationGeneral Classification+3